Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal actions and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MLLoader
    -1.11
    談社
    -0.74
    featureID
    -0.72
     محفوظة
    -0.71
    ValueStyle
    -0.71
    SourceChecksum
    -0.69
    كويكب
    -0.69
    󠁣
    -0.68
    AccessorTable
    -0.67
     ujednoznacz
    -0.67
    POSITIVE LOGITS
    »
    0.59
    We
    0.58
    <eos>
    0.57
    ∣
    0.57
    "
    0.57
    ]
    0.57
    ‍
    0.54
    <strong>
    0.54
    “
    0.53
     sacrament
    0.53
    Act Density 0.015%

    No Known Activations